I am a lead researcher at Stability AI. In the past, I was a researcher at Google Research and Nvidia Research. I completed my PhD at Perceiving Systems department, Max-Planck Institute (MPI) for Intelligent Systems in Tübingen, Germany. My PhD advisor was Prof. Peter V. Gehler. I did my bachelors and masters in Computer Science at IIIT-Hyderabad, India.

My research interests include 3D/4D Computer Vision and Machine Learning. Specifically, I am mainly interested in automatic 3D and 4D object understanding from internet image collections and videos leveraging both reconstruction and generation techniques. In addition, I also work on understanding and generating creative images such as visual metaphors, paintings etc.

If you are interested in joining my 3D team at Stability or research collaborations or internships, please drop me an email with your CV.

News

January, 2024 : A paper on ‘Controllable human motion generation’ accepted to ICLR’24.

January, 2024 : Area chairing for ICML’24 and ECCV’24.

November, 2023 : Joined Stability AI as a 3D research lead.

October, 2023 : Invited talk on ‘3D of Everything from internet image collections’ at ICCV’23 tutorial on Learning with Noisy and Unlabeled Data.

October, 2023 : A paper on ‘Articulated hand-object pose estimation’ (oral) accepted to 3DV’24.

September, 2023 : Papers on ‘Articulated animal reconstruction from noisy internet images (ARTIC3D)’, ‘A dataset of image collections with near-perfect 3D annotations’ (NAVI, benchmark track), ‘Stable diffusion complements Dino for zero-shot semantic correspondences’ and ‘Using LLMs for layout generation (LayoutGPT)’ accepted to NeurIPS’23.

September, 2023 : Area chairing for ICLR’24.

July, 2023 : Papers on ‘DreamBooth3D’, ‘Aligning sparse image collections (ASIC)’ and ‘NeRF and pose optimization (LU-NeRF)’ accepted to ICCV’23.

July, 2023 : Guest editor for IJCV special issue on ‘Large-Scale Generative Models for Content Creation and Manipulation’.

see all news

varunjampani@gmail.com
Stability AI
Boston, MA, USA.

Publications

Refer to my Google Scholar page for a more up-to-date list of publications.

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations

V. Jampani*, K. K. Maninis*, A. Engelhardt, A. Karpur, K. Truong, K. Sargent, S. Popov, A. Araujo, R. M. Brualla, K. Patel, D. Vlasic, V. Ferrari, A. Makadia, C. Liu, Y. Li, H. Zhou (*equal contribution)

Neural Information Processing Systems, NeurIPS’23

pdf / project page / dataset (github)

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

C-H. Yao, A. Raj, W-C. Hung, Y. Li, M. Rubinstein, M-H. Yang, V. Jampani

Neural Information Processing Systems, NeurIPS’23

pdf / project page / code (github)

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

W. Feng*, W. Zhu*, T-J. Fu, V. Jampani, A. Akula, X. He, S. Basu, X. E. Wang, W. Y. Wang (*equal contribution)

Neural Information Processing Systems, NeurIPS’23

pdf / project page / code (github)

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

J. Zhang, C. Herrmann, J. Hur, L. P. Cabrera, V. Jampani, D. Sun, M-H. Yang

Neural Information Processing Systems, NeurIPS’23

pdf / project page / code (github)

DreamBooth3D: Subject-Driven Text-to-3D Generation

A. Raj, S. Kaza, B. Poole, M. Niemeyer, N. Ruiz, B. Mildenhall, S. Zada, K. Aberman, M. Rubinstein, J. Barron, Y, Li, V. Jampani

International Conference on Computer Vision, ICCV’23

pdf / project page / video

ASIC: Aligning Sparse in-the-wild Image Collections

K. Gupta, V. Jampani, C. Esteves, A. Shrivastava, A. Makadia, N. Snavely, A. Kar

International Conference on Computer Vision, ICCV’23

pdf / project page / video

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs

Z. Cheng, C. Esteves, V. Jampani, A. Kar, S. Maji, A. Makadia

International Conference on Computer Vision, ICCV’23

pdf / project page

MetaCLUE: Towards Comprehensive Visual Metaphors Research

A. Akula, B. Driscoll, P. Narayana, S. Changpinyo, Z. Jia, S. Damle, G. Pruthi, S. Basu, L. Guibas, W. T. Freeman, Y. Li, V. Jampani

Computer Vision and Pattern Recognition, CVPR’23

pdf / project page / video

Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble

C-H. Yao, W-C. Hung, Y. Li, M. Rubinstein, M-H. Yang, V. Jampani

Computer Vision and Pattern Recognition, CVPR’23

pdf / project page / video / code (github)

LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding

G. Li, V. Jampani, D. Sun, L. Sevilla-Lara

Computer Vision and Pattern Recognition, CVPR’23

pdf / project page / video / code (github)

DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

N. Ruiz, Y. Li, V. Jampani, Y. Pritch, M. Rubinstein, K. Aberman (oral, best student paper honorable mention)

Computer Vision and Pattern Recognition, CVPR’23

pdf / project page / code (dataset - github)

ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency

Z. Huang, V. Jampani, N. A. Thai, Y. Li, S. Stojanov, J. M. Rehg

Computer Vision and Pattern Recognition, CVPR’23

pdf / project page / video / code (github)

NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs

H. Rangwani, L. Bansal, K. Sharma, T. Karmali, V. Jampani, R. V. Babu

Computer Vision and Pattern Recognition, CVPR’23

pdf / project page / code (github)

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

W. Feng, X. He, T. J. Fu, V. Jampani, A. Akula, P. Narayana, S. Basu, X. E. Wang, W. Y. Wang

International Conference on Learning Representations, ICLR’23

pdf / project page / code (github)

LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery

C-H. Yao, W-C. Hung, Y. Li, M. Rubinstein, M-H. Yang, V. Jampani

Neural Information Processing Systems, NeurIPS’22

pdf / project page / video / code (github)

SAMURAI: Shape and Material from Unconstrained Real-world Arbitrary Image Collections

M. Boss, A. Engelhardt, A. Kar, Y. Li, D. Sun, J. Barron, H. Lensch, V. Jampani

Neural Information Processing Systems, NeurIPS’22

pdf / project page / video / code (github)

Polynomial Neural Fields for Subband Decomposition and Manipulation

G. Yang, S. Benaim, V. Jampani, K. Genova, J. Barron, T. Funkhouser, B. Hariharan, S. Belongie

Neural Information Processing Systems, NeurIPS’22

pdf / code (github)

Subsidiary Prototype Alignment for Universal Domain Adaptation

J. N. Kundu*, S. Bhambri*, A. Kulkarni*, H. Sarkar, V. Jampani, R. V. Babu (*equal contribution)

Neural Information Processing Systems, NeurIPS’22

pdf / project page / video

CPL: Counterfactual Prompt Learning for Vision and Language Models

X. He, D. Yang, W. Feng, T. J. Fu, A. Akula, V. Jampani, P. Narayana, S. Basu, W. Y. Wang, X. E. Wang

Empirical Methods in Natural Language Processing, EMNLP’22

pdf / code (github)

Multi-Frame Video Prediction with Learnable Motion Encodings

R. Jasti, V. Jampani, D. Sun, M-H. Yang

International Conference on Image Processing, ICIP’22

pdf

Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues

Z. Huang, S. Stojanov, A. Thai, V. Jampani, J. M. Rehg

European Conference on Computer Vision, ECCV’22

pdf / project page / code (github)

Improving GANs for Long-Tailed Data through Group Spectral Regularization

H. Rangwani, N. Jaswani, T. Karmali, V. Jampani, R. V. Babu

European Conference on Computer Vision, ECCV’22

pdf / project page / code (github)

Hierarchical Semantic Regularization of Latent Spaces in StyleGANs

T. Karmali, R. Parihar, S. Agrawal, H. Rangwani, V. Jampani, M. Singh, R. V. Babu

European Conference on Computer Vision, ECCV’22

pdf / project page / code (github)

Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation

J. N. Kundu*, S. Bhambri*, A. Kulkarni*, H. Sarkar, V. Jampani, R. V. Babu (*equal contribution)

European Conference on Computer Vision, ECCV’22

pdf / project page / video / code (github)

Balancing Discriminability and Transferability for Source-Free Domain Adaptation

J. N. Kundu*, A. Kulkarni*, S. Bhambri*, D. Mehta, S. Kulkarni, V. Jampani, R. V. Babu (*equal contribution)

International Conference on Machine Learning, ICML’22

pdf / project page / video / code (github)

Learning ABCs: Approximate Bijective Correspondence for Isolating Factors of Variation with Weak Supervision

K. A. Murphy, V. Jampani, S. Ramalingam, A. Makadia

Computer Vision and Pattern Recognition, CVPR’22

pdf / code (github)

SOMSI: Spherical Novel View Synthesis with Soft Occlusion Multi-Sphere Images

T. A. Habtegebrial, C. Gava, M. Rogge, D. Stricker, V. Jampani

Computer Vision and Pattern Recognition, CVPR’22

pdf / project page / video / code (github)

Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation

J. N. Kundu, S. Seth*, Y. Pradyumna*, V. Jampani, A. Chakraborty, R. V. Babu (*equal contribution)

Computer Vision and Pattern Recognition, CVPR’22

pdf / project page / code (gridve)

VIDT: An efficient and effective fully transformer-based object detector

H. Song, D. Sun, S. Chun, V. Jampani, D. Han, B. Heo, W. Kim, M. H. Yang

International Conference on Learning Representations, ICLR’22

pdf / code (github)

Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation

J. N. Kundu*, A. Kulkarni*, S. Bhambri*, V. Jampani, R. V. Babu (*equal contribution)

Association for the Advancement of Artificial Intelligence, AAAI’22

pdf / project page / video


see all publications

Theses

Learning Inference Models for Computer Vision

Learning based techniques for better inference in several computer vision models ranging from inverse graphics to freely parameterized neural networks.

V. Jampani

PhD Thesis, MPI for Intelligent Systems and University of Tübingen, December, 2016

pdf / slides / library

A Study of X-Ray Image Perception for Pneumoconiosis Detection

Eye tracking experimental studies and models for X-Ray Image Perception and Diagnosis.

V. Jampani

Master Thesis, IIIT-Hyderabad, January, 2013

pdf